Feature selection and classification of brain midline tumors using tiny vision transformers and neighborhood component analysis

Abstract

Brain midline tumors pose significant diagnostic challenges due to their complex structure and variability in presentation. In this study, we propose a robust classification framework for detecting brain midline tumors using image classification and feature selection techniques. The images, categorized into positive and negative classes, were processed using the Google Tiny Model Vision Transformer without any additional training. Feature extraction was performed by utilizing the head layer of the Tiny Model Vision Transformer, which yielded 1,000 features from the fully connected layer based on the pre-trained weights of the network. These features were initially classified using classical machine learning classifiers such as support vector machines, k-nearest neighbors and decision trees. To improve classification accuracy and reduce computational costs, Neighborhood Component Analysis was applied as a feature selection method. Neighborhood Component Analysis selected the top 460 most informative features from the initial set of 1,000 features. These selected features were subsequently used for classification, and the performance was compared with the results obtained using the full feature set. The comparative analysis revealed that the Neighborhood Component Analysis-based feature selection significantly enhanced classification accuracy and reduced processing time without sacrificing model reliability. The findings demonstrate that combining Tiny Model Vision Transformers with Neighborhood Component Analysis is an effective approach for brain midline tumor classification, offering a balance between accuracy and computational efficiency. This method holds promise for improving early diagnosis and aiding clinical decision-making, making it a valuable tool in medical image analysis and brain tumor detection.

Keywords

• Brain Midline Tumors
• Image Classification
• Neighborhood Component Analysis
• Vision Transformers

References

1. 1. Hafeez, M. A., C. B. Kayasandik and M. Y. Dogan, Brain tumor classification using MRI images and convolutional neural networks. In 2022 30th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
2. 2. Dosovitskiy, A., et al., An image is worth 16x16 words: Transformers for image recognition at scale. Proceedings of ICLR, 2021.
3. 3. Zhao, J., X. Hou, M. Pan, and H. Zhang, Attention-based generative adversarial network in medical imaging: A narrative review. Computers in Biology and Medicine, 2022. 149: p. 105948.
4. 4. Henry, E.U., O. Emebob, and C.A. Omonhinmin, Vision transformers in medical imaging: A review. arXiv preprint, 2022. arXiv:2211.10043.
5. 5. Tsuneki, M., Deep learning models in medical image analysis. Journal of Oral Biosciences, 2022. 64(3): p. 312–320.
6. 6. He, K., X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition. Proceedings of CVPR, 2016.
7. 7. Cortes, C. and V. Vapnik, Support-vector networks. Machine Learning, 1995. 20: p. 273–297.
8. 8. Park, C.H. and S.B. Kim, Sequential random k-nearest neighbor feature selection for high-dimensional data. Expert Systems with Applications, 2015. 42(5): p. 2336–2342.

9. 9. Goldberger, J., G.E. Hinton, S. Roweis, and R.R. Salakhutdinov, Neighbourhood components analysis. Advances in Neural Information Processing Systems, 2004. 17.
10. 10. Pedregosa, F., et al., Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 2011. 12: p. 2825–2830.
11. 11. Belkin, M. and P. Niyogi, Laplacian eigenmaps and spectral techniques for embedding and clustering. NIPS, 2001. p. 585–591.
12. 12. Krizhevsky, A., I. Sutskever, and G. Hinton, ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012.
13. 13. Wang, Z. and A. Bovik, A universal image quality index. IEEE Signal Processing Letters, 2002. 9(3): p. 81–84.
14. 14. Caruana, R., Multitask learning. Machine Learning, 1997. 28: p. 41–75.
15. 15. Bassel, A., A.B. Abdulkareem, Z.A.A. Alyasseri, N.S. Sani, and H.J. Mohammed, Automatic malignant and benign skin cancer classification using a hybrid deep learning approach. Diagnostics, 2022. 12(10): p. 2472.
16. 16. Bauer, S., et al., A survey of MRI-based medical image analysis for brain tumor studies. Physics in Medicine and Biology, 2013. 58(13): p. 97–129.
17. 17. Pereira, S., A. Pinto, V. Alves, and C.A. Silva, Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Transactions on Medical Imaging, 2016. 35(5): p. 1240–1251.
18. 18. Taha, A.T. and A. Hanbury, Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Medical Imaging, 2015. 15: p. 29.
19. 19. Vaswani, A., et al., Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), 2017. p. 5998–6008.
20. 20. Taghanaki, A., et al., Deep semantic segmentation of natural and medical images: A review. Artificial Intelligence Review, 2021. 54: p. 137–178.
21. 21. Liu, Z., et al., Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021. p. 10012–10022.
22. 22. Mehta, S., X. Lu, W. Wu, D. Weaver, H. Hajishirzi, J.G. Elmore, and L.G. Shapiro, End-to-end diagnosis of breast biopsy images with transformers. Medical Image Analysis, 2022. 79: p. 102466.
23. 23. Ravi, A., V. Chaturvedi, and M. Shafique, Vit4mal: Lightweight vision transformer for malware detection on edge devices. ACM Transactions on Embedded Computing Systems, 2023. 22(5s): p. 1–26.
24. 24. Gumaei, A., M.M. Hassan, M.R. Hassan, A. Alelaiwi, and G. Fortino, A hybrid feature extraction method with regularized extreme learning machine for brain tumor classification. IEEE Access, 2019. 7: p. 36266–36273.
25. 25. Rashid, H.U., T. Ibrikci, S. Paydaş, F. Binokay, and U. Çevik, Analysis of breast cancer classification robustness with radiomics feature extraction and deep learning techniques. Expert Systems, 2022. 39(8): p. e13018.
26. 26. Joliffe, I.T. and B.J.T. Morgan, Principal component analysis and exploratory factor analysis. Statistical Methods in Medical Research, 1992. 1(1): p. 69–95.
27. 27. Fukunaga, K., Introduction to statistical pattern recognition. 2nd ed. Academic Press, 2013.
28. 28. Shalev-Shwartz, S. and S. Ben-David, Understanding machine learning: From theory to algorithms. Cambridge University Press, 2014.
29. 29. Nguyen, M.H. and F. De la Torre, Optimal feature selection for support vector machines. Pattern Recognition, 2010. 43(3): p. 584–591.
30. 30. Gayathri, S., V.P. Gopi, and P. Palanisamy, Automated classification of diabetic retinopathy through reliable feature selection. Physical and Engineering Sciences in Medicine, 2020. 43(3): p. 927–945.
31. 31. Thaha, M.M., K.P.M. Kumar, B.S. Murugan, S. Dhanasekeran, P. Vijayakarthick, and A.S. Selvi, Brain tumor segmentation using convolutional neural networks in MRI images. Journal of Medical Systems, 2019. 43: p. 1–10.
32. 32. Hu, W., et al., A state-of-the-art survey of artificial neural networks for whole-slide image analysis. Computers in Biology and Medicine, 2023. 161: p. 107034.
33. 33. Hamed, S.K., et al., Enhanced feature representation for multimodal fake news detection using localized fine-tuning of improved BERT and VGG-19 models. Arabian Journal for Science and Engineering, 2024. p. 1–17.
34. 34. Fang, Y., et al., You only look at one sequence: Rethinking transformer in vision through object detection. Advances in Neural Information Processing Systems, 2021. 34: p. 26183–26197.
35. 35. Zeng, Z., et al., You only sample (almost) once: Linear cost self-attention via Bernoulli sampling. International Conference on Machine Learning, PMLR, 2021. p. 12321–12332.
36. 36. Khan, S., M. Naseer, M. Hayat, S.W. Zamir, F.S. Khan, and M. Shah, Transformers in vision: A survey. ACM Computing Surveys (CSUR), 2022. 54(10s): p. 1–41.
37. 37. Hassanin, M., et al., Visual attention methods in deep learning: An in-depth survey. Information Fusion, 2024. 108: p. 102417.
38. 38. Li, M., et al., SACNN: Self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network. IEEE Transactions on Medical Imaging, 2020. 39(7): p. 2289–2301.
39. 39. Guo, M.H., et al., Beyond self-attention: External attention using two linear layers for visual tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. 45(5): p. 5436–5447.
40. 40. Prabhakar, J., Vision Transformer-based model for human action recognition in still images. Journal of Computational Analysis and Applications, 2024. 33(8): p. 522–531.
41. 41. Şahin, E., et al., Multi-objective optimization of ViT architecture for efficient brain tumor classification. Biomedical Signal Processing and Control, 2024. 91: p. 105938.
42. 42. Marqo, Introduction to Vision Transformers. [cited 2025 7 February]; Available from: https://www.marqo.ai/course/introduction-to-vision-transformers.
43. 43. Kaggle, P and N classification in midline tumors. [cited 2025 7 February]; Available from: https://www.kaggle.com/datasets/vuppalaadithyasairam/p-and-n-classification-in-midline-tumors.